FD-GAN: Pose-guided Feature Distilling GAN

for Robust Person Re-identification

Yixiao Ge1*      Zhuowan Li2,3*      Haiyu Zhao2      Guojun Yin2,4      Shuai Yi2      Xiaogang Wang1      Hongsheng Li1     
1. Multimedia Laboratory, The Chinese University of Hong Kong           2. SenseTime Research          
3. Johns Hopkins University           4. University of Science and Technology of China          
Conference on Neural Information Processing Systems (NeurIPS) 2018


Person re-identification (reID) is an important task that requires to retrieve a person’s images from an image dataset, given one image of the person of interest. For learning robust person features, the pose variation of person images is one of the key challenges. Existing works targeting the problem either perform human alignment, or learn human-region-based representations. Extra pose information and computational cost is generally required for inference. To solve this issue, a Feature Distilling Generative Adversarial Network (FD-GAN) is proposed for learning identity-related and pose-unrelated representations. It is a novel framework based on a Siamese structure with multiple novel discriminators on human poses and identities. In addition to the discriminators, a novel same-pose loss is also integrated, which requires appearance of a same person’s generated images to be similar. After learning pose-unrelated person features with pose guidance, no auxiliary pose information and additional computational cost is required during testing. Our proposed FD-GAN achieves state-of-the-art performance on three person reID datasets, which demonstrates that the effectiveness and robust feature distilling capability of the proposed FD-GAN.


  title={FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification},
  author={Ge, Yixiao and Li, Zhuowan and Zhao, Haiyu and Yin, Guojun and Yi, Shuai and Wang, Xiaogang and Li, Hongsheng},
  booktitle={Advances in Neural Information Processing Systems},